© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33485
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

    np_acts-logits-general · gemini-2.5-flash-lite

    technical skills and trends

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    0.50
    Touch
    0.50
    isable
    0.50
    irt
    0.48
    Edge
    0.45
     streak
    0.44
    urch
    0.43
    Touchable
    0.43
    i
    0.43
    Flare
    0.43
    POSITIVE LOGITS
     indicó
    0.58
     avenida
    0.54
    エスト
    0.52
     dientes
    0.51
     alguns
    0.50
    ウィ
    0.50
     santo
    0.50
    帕
    0.50
     sabes
    0.50
     segundos
    0.50
    Activations Density 0.000%

    No Known Activations